{"id":"https://openalex.org/W4302774970","doi":"https://doi.org/10.23919/sice56594.2022.9905866","title":"Centralized Training with Decentralized Execution Reinforcement Learning for Cooperative Multi-agent Systems with Communication Delay","display_name":"Centralized Training with Decentralized Execution Reinforcement Learning for Cooperative Multi-agent Systems with Communication Delay","publication_year":2022,"publication_date":"2022-09-06","ids":{"openalex":"https://openalex.org/W4302774970","doi":"https://doi.org/10.23919/sice56594.2022.9905866"},"language":"en","primary_location":{"id":"doi:10.23919/sice56594.2022.9905866","is_oa":false,"landing_page_url":"https://doi.org/10.23919/sice56594.2022.9905866","pdf_url":null,"source":{"id":"https://openalex.org/S4363608498","display_name":"2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113638652","display_name":"Takuma Ikeda","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takuma Ikeda","raw_affiliation_strings":["University of Tsukuba,Master’s Program in Intelligent and Mechanical Interaction Systems,Ibaraki,Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Master’s Program in Intelligent and Mechanical Interaction Systems,Ibaraki,Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101693065","display_name":"Takeshi Shibuya","orcid":"https://orcid.org/0000-0003-4645-5898"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Shibuya","raw_affiliation_strings":["University of Tsukuba,Faculty of Engineering, Information and Systems,Ibaraki,Japan","Faculty of Engineering, Information and Systems, University of Tsukuba, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Faculty of Engineering, Information and Systems,Ibaraki,Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"Faculty of Engineering, Information and Systems, University of Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113638652"],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":1.6694,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.86226815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"135","last_page":"140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7893799543380737},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7316192388534546},{"id":"https://openalex.org/keywords/communications-system","display_name":"Communications system","score":0.5681471824645996},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5300825834274292},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5051196217536926},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.46057984232902527},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4364360272884369},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2900976538658142},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2239571511745453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893799543380737},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7316192388534546},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.5681471824645996},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5300825834274292},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5051196217536926},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.46057984232902527},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4364360272884369},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2900976538658142},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2239571511745453},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/sice56594.2022.9905866","is_oa":false,"landing_page_url":"https://doi.org/10.23919/sice56594.2022.9905866","pdf_url":null,"source":{"id":"https://openalex.org/S4363608498","display_name":"2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.800000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2012812921","https://openalex.org/W2095701584","https://openalex.org/W2099618002","https://openalex.org/W2101956270","https://openalex.org/W2157331557","https://openalex.org/W2395575420","https://openalex.org/W2530849036","https://openalex.org/W2588790649","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2981207549","https://openalex.org/W2994864869","https://openalex.org/W3111778277","https://openalex.org/W4295598622","https://openalex.org/W4301501993","https://openalex.org/W6675518749","https://openalex.org/W6712181171","https://openalex.org/W6749304979","https://openalex.org/W6769091550","https://openalex.org/W6864424756"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W2233261550","https://openalex.org/W4380318855","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2138720691","https://openalex.org/W2997094352","https://openalex.org/W2031695474"],"abstract_inverted_index":{"In":[0,72],"cooperative":[1,63,82],"multi-agent":[2,64,83],"systems,":[3],"efficient":[4],"coordination":[5],"among":[6],"agents":[7,23],"is":[8,14,54],"important":[9],"when":[10],"accomplishing":[11],"tasks.":[12],"VFFAC":[13],"a":[15,48,62,77,81,91,100,134],"method":[16,38,101,120],"that":[17,117],"learns":[18,122],"the":[19,28,58,108,118],"communication":[20,67,104,135],"system":[21,65,84],"between":[22],"and":[24,90],"their":[25],"interactions":[26],"with":[27,33,47,66,85,124,133],"environment":[29,88,132],"to":[30,102],"obtain":[31],"policies":[32],"high":[34,125],"performance.":[35],"However,":[36],"this":[37,73],"results":[39],"in":[40,45,50,69,80,95,130],"decreased":[41],"performance":[42],"of":[43,57,61,110],"policy":[44,123],"environments":[46],"delay":[49,94],"communication.":[51,96,114],"Furthermore,":[52],"there":[53],"no":[55],"formulation":[56],"control":[59],"problem":[60,79],"delays":[68,105],"unknown":[70,87],"environments.":[71],"study,":[74],"we":[75],"formulated":[76],"decision-making":[78],"an":[86,131],"model":[89],"certain":[92],"length":[93],"We":[97,115],"also":[98],"propose":[99],"handle":[103],"by":[106],"using":[107],"history":[109],"information":[111],"obtained":[112],"through":[113,127],"demonstrated":[116],"proposed":[119],"successfully":[121],"rewards":[126],"simulated":[128],"experiments":[129],"delay.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}